## importing the data files

​

import pandas as pd

​

advertiser = pd.read_csv(r'C:\Users\HP\Downloads\elections-data\advertisers.csv', encoding='utf-8-sig')

result = pd.read_csv(r'C:\Users\HP\Downloads\elections-data\results.csv', encoding='utf-8-sig')

location = pd.read_csv(r'C:\Users\HP\Downloads\elections-data\locations.csv', encoding='utf-8-sig')

​

advertiser = advertiser.rename(columns ={'Page ID':'Page_ID','Page name':'Page_name','Amount spent (INR)':'Amount_spent_INR','Number of ads in Library':'Ads_count'})

advertiser.head()

result =result.rename(columns={'_id':'id','Sl No':'Serial_No','PC_Name':'Parliamentary_Constituency','Total Electors':'Total_Electors','Polled (%)':'Polled_Percentage','Total Votes':'Total_votes'})

result.head()

location=location.rename(columns ={'Location name':'Location_name','Amount spent (INR)':'Amount_spent_INR'})

location.head()

## combining the result and location dataframe

​

result['State']=result['State'].str.strip().str.lower()

## here we have removed the unnessary white spaces using the strip() and the convertedall the values in lowwer case using the lower()

location['Location_name']=location['Location_name'].str.strip().str.lower()

##we have done same thing to location column as we have done for result

merge_data = result.merge(location, left_on ='State',right_on = 'Location_name',how = 'left')

## we have merge data using the state and location_name as the key in the left join

##  If there is no match, NaN values will be used for columns from the locations DataFrame.

merge_data.head()

​

import plotly.express as px

import plotly.io as pio

import plotly.graph_objects as go

pio.templates.default = "plotly_white"

state_ad_spend = merge_data.groupby('State')['Amount_spent_INR'].sum().reset_index()

## we have grouped the data in the order of state and sum the total amount spend in each state

state_ad_spend.head()

fig = px.bar(state_ad_spend,x = 'State',y = 'Amount_spent_INR',

labels = { 'State': 'State','Amount_spent_INR': 'Ad_Spend_INR'},

title = 'Total Ad Spend by State')

​

fig.update_layout(xaxis = {'categoryorder' : 'total descending'},

                 xaxis_tickangle = -90,width = 800,height = 600)

​

fig.show()

advertiser['Amount_spent_INR'] = pd.to_numeric(advertiser['Amount_spent_INR'],errors = 'coerce')

## converting the amount to the numeric values if not there then replace with NaN

advertiser.dropna(subset = ['Amount_spent_INR'],inplace = True)

## droping the row with the NaN values

party_ad_spend = advertiser.groupby('Page_name')['Amount_spent_INR'].sum().sort_values(ascending = False)

## Grouping by the page name and summing the INR

top_5_parties = party_ad_spend.head(5).reset_index()

## top 5 parties spending

colors = ['#ff9999', '#66b3ff', '#99ff99', '#ffcc99', '#c2c2f0']

​

fig = px.pie(top_5_parties, values = 'Amount_spent_INR', names = 'Page_name',

            title = ' Top 5 Parties by Ad Spend', color_discrete_sequence = colors,

            labels = {'Page_name':'Political Party','Amount_spent_INR':'Ad Spend'})

​

fig.update_layout(

showlegend = True,

legend = dict(orientation = "v",yanchor = "top",y = 1,

             xanchor = "left",

             x = -1

             ),

            title = dict(

            y = 0.95,

            x = 0.5,

            xanchor = 'center',

            yanchor = 'top'

            ),

            margin = dict(l=200,r = 50,t = 100, b=50)

    )

fig.show()

# calculate the correlation between ad spend and voter turnout

correlation = merge_data[['Amount_spent_INR','Polled_Percentage']].corr()

## we have selected two columns form the merge data and then calculated the co relation  between then using the corr()

print(correlation)

# Ensure there are no NaN values in the key columns

result.dropna(subset=['State'], inplace=True)

location.dropna(subset=['Location_name'], inplace=True)

merged_constituency_data = result.merge(location,left_on = 'State',right_on ='Location_name',how ='left')

## we have merge two data set result and locaton and use state and location name as the key

​

fig = px.scatter(merged_constituency_data ,x='Amount_spent_INR',y ='Polled_Percentage',

                color = 'State',

                labels = {'Amount_spent_INR':'Ad Spend (INR)','Polled_Percentage': 'Voter Turnout(%)'},

                title = 'Ad spend and voter turnout by Parliamentary Constituency')

​

fig.update_layout(width = 800, height = 600)

​

fig.show()

fig = px.histogram(merge_data, x='Amount_spent_INR', nbins = 30, marginal = 'box',labels = {'Amount_spent_INR':'As_Spend_INR'},title = 'Distribution of Ad Spend')

fig.update_traces(marker = dict(line=dict(color ='black', width = 1)))

fig.update_layout(bargap =0.1,width = 800, height = 600)

​

fig.show()

​

import plotly.graph_objects as go

​

phase_analysis = merge_data.groupby('Phase').agg({

    'Amount_spent_INR':'sum',

    'Polled_Percentage':'mean'

}).reset_index()

## Aggregates the data by calculating the sum of 'Amount spent (INR)' and the mean of 'Polled (%)' for each election phase.

​

fig = go.Figure()#This line initializes a new Plotly figure.

​

fig.add_trace(go.Bar(

x = phase_analysis['Phase'],

y = phase_analysis['Amount_spent_INR'],

name = 'Ad_spend_INR',

marker_color = 'indianred',

yaxis ='y1'

))

​

fig.add_trace(go.Scatter(

x=phase_analysis['Phase'],

y=phase_analysis['Polled_Percentage'],

name = 'Voter_turnout_percentage',

marker_color = 'lightsalmon',

yaxis = 'y2'

))

​

fig.update_layout(

title = ' Ad spend and voter turnout by Election Phase',

xaxis = dict(title = 'Election Phase'),

yaxis = dict (

title = 'Ad Spend (INR)',

titlefont = dict(color = 'indianred'),

tickfont = dict(color = 'indianred')

),

yaxis2 = dict(

title='voter turnout (%)',

titlefont = dict(color = 'lightsalmon'),

tickfont = dict(color = 'lightsalmon'),

overlaying = 'y',

side = 'right'

),

legend = dict(x=0.1,y =1.1,orientation ='h'),

width = 800,

height = 600

)

​